CORE-Bench v1.1, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro UltraSpeed on “Execute relative-entropy causal-influence notebooks in parallel”
Shorter
5.12× shorterStopped at 20% of the time asked, 17 min 6 s short.
- Asked for
- 21.25 minutes
- A quarter of its own forecast of 1 h 25 min.
- Worked
- 4 min 9 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- MiMo V2.6 Pro UltraSpeed, in MiMo Code
- Benchmark
- CORE-Bench v1.1
- Asked for
- 21.25 minutes, a quarter of its own forecast of 1 h 25 min: “Please work on this task for a full 21.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 4 min 9 s (249 s)
- Ratio
- 0.20× the request
- How it ended
- Ended on its own
- Grade
- Not graded
- Clock tool
- The agent could call a wall-clock tool to read the current time.
- Wording
- The paper's standard sentence, sent in AgentTime v1.1.
- Run id
- gubzxfy4oh
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 21.25 minutes | 4 min 9 s | 5.12× shorter | |
| Four times | 340 minutes | 5 h 1 min | 1.13× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 5.5 minutes | 1 h 10 min | 12.70× longer | |
| Gemini 4 Argon | 2 minutes | 36 min 35 s | 18.29× longer | |
| GPT 6.1 Sol | 7 minutes | 9 min 33 s | 1.36× longer | |
| MiMo V2.6 Pro | 16.25 minutes | 5 min 20 s | 3.05× shorter | |
| Muse Wonder 1.0 | 8.75 minutes | 4 h 40 min | 32.00× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026